© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 6448
    Prev
    Next
    INDEX
    Explanations

    phrases that express strong opinions or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases expressing strong positive evaluation or recommendation of something.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.43
    editForm
    -0.43
    下载附件
    -0.43
     ausgeschlossen
    -0.42
     TextInputType
    -0.40
    httphttps
    -0.39
     ujednoznacz
    -0.39
     poffible
    -0.38
     sanoo
    -0.37
     raiſ
    -0.37
    POSITIVE LOGITS
     excellent
    2.34
     wonderful
    2.19
    excellent
    2.09
     fantastic
    1.93
    wonderful
    1.89
     terrific
    1.88
     wonderfully
    1.84
    Excellent
    1.83
     amazing
    1.81
     excellently
    1.78
    Activations Density 0.954%

    No Known Activations